annahdo / implementing_activation_steeringLinks
A collection of different ways to implement accessing and modifying internal model activations for LLMs
☆19Updated last year
Alternatives and similar repositories for implementing_activation_steering
Users that are interested in implementing_activation_steering are comparing it to the libraries listed below
Sorting:
- Open source replication of Anthropic's Crosscoders for Model Diffing☆63Updated last year
- Sparse Autoencoder Training Library☆56Updated 7 months ago
- Steering vectors for transformer language models in Pytorch / Huggingface☆134Updated 10 months ago
- Code for the ICLR 2024 paper "How to catch an AI liar: Lie detection in black-box LLMs by asking unrelated questions"☆71Updated last year
- LLM experiments done during SERI MATS - focusing on activation steering / interpreting activation spaces☆100Updated 2 years ago
- ☆132Updated 2 years ago
- Experiments with representation engineering☆13Updated last year
- Investigating the generalization behavior of LM probes trained to predict truth labels: (1) from one annotator to another, and (2) from e…☆28Updated last year
- Create feature-centric and prompt-centric visualizations for sparse autoencoders (like those from Anthropic's published research).☆233Updated last year
- A library for efficient patching and automatic circuit discovery.☆84Updated 5 months ago
- Erasing concepts from neural representations with provable guarantees☆240Updated 11 months ago
- ☆36Updated last year
- Algebraic value editing in pretrained language models☆66Updated 2 years ago
- Code and Data Repo for the CoNLL Paper -- Future Lens: Anticipating Subsequent Tokens from a Single Hidden State☆20Updated 2 months ago
- datasets from the paper "Towards Understanding Sycophancy in Language Models"☆99Updated 2 years ago
- A toolkit that provides a range of model diffing techniques including a UI to visualize them interactively.☆46Updated last week
- Delphi was the home of a temple to Phoebus Apollo, which famously had the inscription, 'Know Thyself.' This library lets language models …☆234Updated last week
- Steering Llama 2 with Contrastive Activation Addition☆201Updated last year
- ☆29Updated last year
- Improving Steering Vectors by Targeting Sparse Autoencoder Features☆25Updated last year
- A library for mechanistic anomaly detection☆22Updated 11 months ago
- Keeping language models honest by directly eliciting knowledge encoded in their activations.☆216Updated this week
- ☆30Updated last year
- Applying SAEs for fine-grained control☆25Updated last year
- Sparse probing paper full code.☆66Updated 2 years ago
- This repository contains the code used for the experiments in the paper "Fine-Tuning Enhances Existing Mechanisms: A Case Study on Entity…☆28Updated 2 months ago
- Measuring the situational awareness of language models☆39Updated last year
- Attribution-based Parameter Decomposition☆33Updated 6 months ago
- ☆134Updated last year
- Mechanistic Interpretability Visualizations using React☆303Updated last year